-
Notifications
You must be signed in to change notification settings - Fork 2.8k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How to crop a large picture into small pictures and predict #44
Comments
@lyw615 There is no this operation now. Maybe can refer multi-scale in face-detection: https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.1/tools/face_eval.py#L75 But different from face-detection, can make the multi images with 512 x 512 into a batch, then do predict. |
According to #39 , you use YOLOv3. If only for prediction, you also can export model, refer https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.1/docs/EXPORT_MODEL.md . Then refer following code to add multi-scale predcition. I think this may be easier than modify the data-feed.
|
Thank you very much.After tried, i'll give the reply |
FYI, the
detection bbox will be rescale to image shape 608*608 , if you want to get the predict bbox in original image shape scale, set
|
output format of thie code please refer to https://www.paddlepaddle.org.cn/documentation/docs/en/api/layers/multiclass_nms.html |
The size of images for prediction is normally 3600*2400.The effect of directly entering the network for prediction is not as good as expected. Existing model settings are enough good, so I don't need to export the model. I just want to explore the way cropping the largesize image into multi smaller image. And whether there will be a better result |
Can i only crop a large size image into some smaller size array for prediction,rather than some image.This is my original intention |
|
Please make sure the path exist. |
If only test one cropped image, and still want to use then change
I'm sorry if I did not fully understanding what your mean. |
Dirname means absolute path for vehicle_yolov3_darknet? Which is weight path of infer.py |
|
为了说清楚一点,我还是用中文: 上面其实提到的是两种方式,
运行完,你会在 |
现在设定的图像维度(3,608,608)其实对于我的数据预测效果算不错了,只是我的数据尺寸过大,所以想试试把读入的图像数组切成几块放进去预测效果会不会更好。导出模型的维度成YoloTestFeed.image_shape=[3,320,320],会不会难以复现目前这个项目设定参数的效果啊?我可以导出成(3,608,608)的吗 |
|
|
related to #46 |
按照您这边提供的代码,#44 (comment)
配置信息:win7 |
Such as a image with 36002400 cropped into multi images with 512 512,then feed all of them into the model.The api is encapsulated too deeply, I can't find where to modify it.
The text was updated successfully, but these errors were encountered: